Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    ForSegue
    -0.06
    _coef
    -0.06
     pancre
    -0.06
    (classes
    -0.06
    Compatible
    -0.06
     المدر
    -0.06
    _secure
    -0.06
    ΙΝ
    -0.06
    ocrine
    -0.06
    POSITIVE LOGITS
     //}↵↵
    0.08
     amore
    0.07
     xhr
    0.07
     ):↵
    0.07
    }";↵↵
    0.06
    HWND
    0.06
    reater
    0.06
     Brands
    0.06
    лем
    0.06
     twist
    0.06
    Act Density 0.141%

    No Known Activations